机器视觉技术通过视觉采集和分析系统对外界环境进行实时图像采集和处理，得到目标的特征信息，最终实现外部设备的控制。机器视觉技术具有精度高、实时性强、自动化与智能化程度高的优点，已广泛应用于机器人控制、工业生产、辅助医疗诊断等领域。随着医疗技术的发展，机器视觉作为人工智能的重要分支，在康复领域也得到越来越多的应用。本文综述了机器视觉的基本结构和工作原理，并对其在辅助辅具、肢体康复、心理康复等五种康复领域的常见应用进展状况进行简要归纳与介绍，最后总结了机器视觉应用于康复领域的主要问题和发展趋势。

[1] 中国残疾人联合会. 2019年残疾人事业发展统计公报[R/OL].(2020-04-02)[2020-07-02]. http://www.cdpf.org.cn//zwgk/zccx/tjgb0aeb930262974effaddfc41a45ceef58.htm.

[2]? 余文勇,石绘.机器视觉自动检测技术 [M]. 北京: 化学工业出版社 ,2013.

[3]? 工控帮教研组.机器视觉原理与案例详解[M]. 北京：电子工业出版社,2020.

[4] 黄志鹏, 郁汉琪, 张聪,等. 机器视觉的发展及应用[J]. 信息与电脑, 2020(17): 127-129.

Huang ZP, Yu HQ, Zhang C, et al. The development and application of machine vision[J]. China computer& Communication, 2020(17): 127-129.

[5] 赵霞,袁家政，刘宏哲．基于视觉的目标定位技术的研究进展[J]．计算机科学,2016,43(6):10-16,43.

Zhao X, Yuan JZ, Liu HZ. Advances in vision-based target location technology[J]. Computer Science, 2016,43(6):10-16,43.

[6] 杨晨曦，华云松．基于双目立体视觉的目标物测距研究[J]．软件，2020,41(1):128-132.

Yang CX, Hua YS. Research on target ranging based on binocular stereo vision[J]. Computer Engineering & Software,2020,41(1):128-132.

[7]? 周莹亮. 基于计算机视觉的轮椅跟随控制系统研究[D]. 西安：陕西科技大学, 2020.

Zhou YL. Research on wheelchair following control system based on computer vision[D]. Xi’an: Shaanxi University of science and technology, 2020.

[8] 任恒乐, 徐方, 邸霈,等. 基于深度相机的移动机器人自主跟随技术[J]. 计算机工程与设计, 2020, 41(2): 562-566.

Ren HL, Xu F, Di P, et al. Autonomous following technology of mobile robot based on depth camera [J]. Computer Engineering and Design, 2020, 41(2): 562-566.

[9]邹超, 汪秉文, 孙志刚. 基于机器视觉的织物疵点检测方法综述[J]. 天津工业大学学报, 2009, 28(2): 78-82, 85.

Zou C, Wang BW, Sun ZG. Survey on fabric defect detection based on machine vision[J]. Journal of Tianji Polytechnic University, 2009, 28(2): 78-82, 85.

[10] Wang YN, Lu X, Ling ZG, et al. A method to calibrate vehicle-mounted cameras under urban traffic scenes[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(6): 3270-3279.

[11] Zhang ZY. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.

[12] Yuan XC, Wu LS, Peng QJ. An improved Otsu method using the weighted object variance for defect detection[J]. Applied Surface Science, 2015, 349: 472-484.

[13]Girshick R, Donahue J, Darrell T, et al. Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 142-158.

[14] Gorai AK, Raval S, Patel AK, et al. Design and development of a machine vision system using artificial neural network-based algorithm for automated coal characterization[J]. International Journal of Coal Science & Technology, 2020: 1-19.

[15] 赵月鹏. 基于机器视觉的人体坐姿检测系统的设计与实现[D]. 哈尔滨: 哈尔滨理工大学, 2020.

Zhao YP. Design and implementation of human sitting posture detection system based on machine vision[D]. Harbin: Harbin University of science and technology, 2020.

[16] 李旻择, 李小霞, 王学渊,等. 基于多尺度核特征卷积神经网络的实时人脸表情识别[J]. 计算机应用, 2019, 39(9): 2568-2574.

Li MZ, Li XX, Wang XY, et al. Real-time facial expression recognition based on convolutional neural network with multi-scale kernel feature[J]. Journal of Computer Applications, 2019, 39(9): 2568-2574.

[17] 刘勇, 李杰, 张建林,等. 基于深度学习的二维人体姿态估计研究进展[J]. 计算机工程,2021,47(3): 1-16.

Liu Y, Li J, Zhang JL, et al. Research progress of two-dimensional human pose estimation based on deep learning[J]. Computer Engineering, 2021, 47(3): 1-16.

[18]郑季炜. 基于机器视觉的智能人机交互技术研究 [J]. 海峡科学 ,2018(1): 24-26.

[19] Hartman A, Nandikolla VK. Human-machine interface for a smart wheelchair[J]. Journal of Robotics, 2019, 2019: 4837058.

[20] 李杰. 康复机器人辅助患者起立轨迹预测方法研究[D].沈阳: 沈阳工业大学, 2017.

Li J. Research on prediction method of rehabilitation robot assisted patient standing-up trajectory[D]. Shenyang: Shenyang University of technology, 2017.

[21]? Ustinova KI, Perkins J, Szostakowski L. Effect of viewing angle on arm reaching while standing in a virtual environment: potential for virtual rehabilitation [J]. Acta Psychologica, 2010, 133(2): 180-190.

[22] 祝敏航.基于机器视觉的下肢外骨骼康复运动检测系统[D]. 杭州：浙江大学,2016.

Zhu MH. Machine vision-based motion detecting system for rehabilitation of lower extremity exoskeleton[D]. Hangzhou: Zhejiang University, 2016.

[23] 闫航. 康复训练场景下的动作与行为识别方法研究[D]. 郑州：郑州大学, 2020.

Yan H. Research on the method of action and behavior recognition in rehabilitation training[D]. Zhengzhou：Zhengzhou University,2020.

[24] Adriella A, Alenyà G, Hernández-farigola J, et al. Deciding the different robot roles for

patient? cognitive? training[J].? International? Journal? of? Human-Computer? Studies,? 2018, 117: 20-29.

[25]陈浩东. 基于机器视觉的认知康复机器人系统设计[D]. 合肥: 合肥工业大学, 2019.

Chen HD. Design of cognitive rehabilitation robotic system based on machine vision[D]. Hefei: Hefei University of Technology, 2019.

[26] 谢俊祥, 张琳. 智能手术机器人及其应用[J]. 中国医疗器械信息, 2015(3): 11-17.

Xie JX, Zhang L. The review and application of smart and surgical robots[J]. China Medical Device Information, 2015(3): 11-17.

[27] 郑红杰. 基于视觉的手术机器人腹腔镜位姿自动调节方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2018.

Zheng HJ. Research on the laparoscopic pose vision-based automatic adjustment for robot assisted surgery[D]. Harbin: Harbin Engineering University, 2018.

[28] 彭璟, 罗浩宇, 赵淦森, 等. 深度学习下的医学影像分割算法综述[J]. 计算机工程与应用, 2021,57(3):44-57.

Peng J, Luo HY, Zhao GS, et al. Survey of medical image segmentation algorithm in deep learning[J]. Computer Engineering and Applications, 2021, 57(3): 44-57.

[29] 李鹏. 基于3D打印扁平足个性化矫正鞋垫的设计及其对平衡能力的影响[D]. 苏州: 苏州大学,2017.

Li P. The design of personalized orthopedic insoles for flatfoot based on 3D print and its impact on balance ability[D]. Suzhou: Soochow University, 2017.

[30]Germany EI, Pino EJ, Aqueveque PE. Myoelectric intuitive control and transcutaneous electrical stimulation of the forearm for vibrotactile sensation feedback applied to a 3Dprinted prosthetic hand[J]. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2016, 2016: 5046-5050.

[31] 鲁德志, 梅钊, 李向磊,等. 3D打印脊柱侧凸矫形器的数字化设计及效果评估[J]. 中国组织工程研究, 2021,25(9):1329-1334.

Lu DZ, Mei Z, Li XL, et al. Digital design and effect evaluation of three-dimensional printing scoliosis orthosis[J]. Chinese Journal of Tissue Engineering Research, 2021,25(9):1329-1334.

[32]Choo YJ, Boudier-Revéret M, Chang MC. 3D printing technology applied to orthosis manufacturing: narrative review[J]. Annals of Palliative Medicine, 2020, 9(6):4262-4270.

[33]Portnoy S, Barmin N, Elimelech M, et al. Automated 3D-printed finger orthosis versus manual orthosis preparation by occupational therapy students: Preparation time, product weight, and user satisfaction[J]. Journal of Hand Therapy, 2020,33(2): 174-179.

[34] 顾飞，姚庆强，刘帅,等. 3D 打印截骨导板在膝关节单髁 置换术中的应用[J]. 中国数字医学，2020, 15(6): 97-100.

Gu F, Yao QQ, Liu S, et al. Application of 3D-printed osteotomy guide plate in unicompartmental knee arthroplasty[J]. China Digital Medicine, 2020,15（6）：97-100.

[35] 杨勇，邱志杰，徐红革,等.3D 打印结合数字化设计在髋臼骨折手术治疗中的应用[J]. 临床骨科杂志, 2021,24(1): 88-92.

Yang Y, Qiu ZJ, Xu HG, et al. The application of 3D printing combined with digital design in the surgical treatment of acetabular fracture[J]. Journal of Clinical Orthopaedics, 2021,24(1): 88-92.

[36]Raisian S, Fallahi HR, Khiabani KS, et al. Customized titanium mesh based on the 3D printed model vs. manual intraoperative bending of titanium mesh for reconstructing of orbital bone fracture: a randomized clinical trial[J]. Reviews on Recent Clinical Trials，2017，12（3）：154-158.

[37] 高源. 三维模型和机器视觉结合的3D打印医疗导板质量检测[D]. 北京: 北京工业大学, 2016.

Gao Y. The quality evaluation of 3D printing medical guide combining 3D model and computer vision[D]. Beijing: Beijing University of Technology, 2016.

?